add tokenizer

vocab.json

@@ -1 +1 @@
-{"v": 0, "j": 1, "'": 2, "y": 3, "k": 4, "w": 5, "n": 6, "x": 7, "r": 8, "a": 10, "b": 11, "e": 12, "t": 13, "p": 14, "f": 15, "o": 16, "d": 17, "g": 18, "q": 19, "c": 20, "m": 21, "h": 22, "s": 23, "l": 24, "u": 25, "z": 26, "i": 27, "|": 9, "[UNK]": 28, "[PAD]": 29}
+{"y": 0, "v": 1, "x": 2, "q": 3, "p": 4, "w": 5, "r": 6, "u": 7, "l": 8, "z": 9, "f": 10, "m": 11, "'": 12, "i": 13, "e": 14, "h": 15, "t": 16, "c": 17, "k": 18, "g": 19, "n": 20, "b": 21, "j": 22, "o": 23, "d": 25, "a": 26, "s": 27, "|": 24, "[UNK]": 28, "[PAD]": 29}